module 03 / 08
Retrieval & RAG
Learn semantic retrieval, chunking, and grounded generation as one system.
the point
Retrieval and generation fail together in real products. Treating them as one layer makes it easier to debug relevance, citations, and answer quality.
start here
go deeper
understanding check
You should be able to…
- explain semantic search and cosine similarity
- choose a chunking strategy for a document type
- inspect retrieved context before blaming the model
- separate retrieval quality from answer quality
- create a small eval set for grounded answers
prove it by building
Build a cited knowledge assistant
intermediate · next.js or python, embeddings API, sqlite or a vector store, model API
make
a local app that searches a document folder and answers with citations
definition of done
include retrieval logs, citations, and ten grounded-answer evals with pass/fail notes